Stable Diffusion

On this page, we’ll dive into the stable diffusion tasks that are available in the PeerAI API.

Headers

  • Name
    x-api-group(optional)
    Type
    string, default 'main'
    Description

    The id of the peer-ai compute group you want to run this compute on.

  • Name
    x-api-key
    Type
    string
    Description

    The API key for your PeerAI account.

Stable Diffusion

Stable Diffusion is a generative model that can generate high-resolution images based on a given prompt and additional parameters.

  • For Stable Diffusion 1.4, use CompVis/stable-diffusion-v1-4 with
model_options = {
    revision: 'onnx',
    quantized: false
}
  • For Stable Diffusion 1.5, use runwayml/stable-diffusion-v1-5 with
model_options = {
    revision: 'onnx',
    quantized: false
}
  • For Stable Diffusion 2.1, use aislamov/stable-diffusion-2-1-base-onnx with
model_options = {
    revision: 'main',
    quantized: false,
    timestepType: 'float32'
}

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'sentiment-analysis', 'text-classification'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    model_options(optional)
    Type
    object, default null
    Description

    An object containing the following properties:

    • revision (string): The revision of the model to use. e.g., 'main', 'onnx', 'quantized'
    • quantized (boolean): Whether to use the quantized version of the model.
    • timestepType (string): The timestep type of the model. e.g., 'float32', 'int64'
  • Name
    inputs.0
    Type
    object
    Description

    An object containing the following properties:

    • prompt (string): The text prompt to generate the image.
    • strength (number): The strength of the prompt influence on the generated image. Should be between 0 and 1.
    • n_steps (number): The number of steps to run the diffusion process.
    • n_samples (number): The number of samples to generate.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"stable-diffusion\", \"model\": \"runwayml/stable-diffusion-v1-5\", \"model_options\": {\"revision\": \"onnx\", \"quantized\": false }, \"inputs\": {\"prompt\": \"Face of a yellow cat, high resolution, sitting on a park bench.\", \"strength\": 0.6, \"n_steps\": 10, \"n_samples\": 1 }}"

Response

[
  {
    "url": "blob:https://compute.peer-ai.com/55a46563-4372-4a97-9832-ac6bdff1b09f"
  }
]

Stable Diffusion Image to Image

Stable Diffusion Image to Image is a generative model that can generate high-resolution images based on a given prompt, image and additional parameters.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'sentiment-analysis', 'text-classification'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    model_options(optional)
    Type
    object, default null
    Description

    An object containing the following properties:

    • revision (string): The revision of the model to use. e.g., 'main', 'onnx', 'quantized'
    • quantized (boolean): Whether to use the quantized version of the model.
    • timestepType (string): The timestep type of the model. e.g., 'float32', 'int64'
  • Name
    inputs.0
    Type
    object
    Description

    An object containing the following properties:

    • prompt (string): The text prompt to generate the image.
    • strength (number): The strength of the prompt influence on the generated image. Should be between 0 and 1.
    • n_steps (number): The number of steps to run the diffusion process.
    • n_samples (number): The number of samples to generate.
    • image (string): The URL of an image to use as a conditioning input.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"stable-diffusion\", \"model\": \"runwayml/stable-diffusion-v1-5\", \"model_options\": {\"revision\": \"onnx\", \"quantized\": false }, \"inputs\": {\"prompt\": \"Face of a yellow cat, high resolution, sitting on a park bench.\", \"strength\": 0.6, \"n_steps\": 10, \"n_samples\": 1, \"image\": \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png\"}}"

Response

[
  {
    "url": "blob:https://compute.peer-ai.com/55a46563-4372-4a97-9832-ac6bdff1b09f"
  }
]

Stable Diffusion Inpainting

Stable Diffusion is a technique used for image inpainting, which involves filling in missing or corrupted parts of an image. It uses a generative model to generate plausible content for the missing regions based on the surrounding context.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'stable-diffusion'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    model_options(optional)
    Type
    object, default null
    Description

    An object containing the following properties:

    • revision (string): The revision of the model to use. e.g., 'main', 'onnx', 'quantized'
    • quantized (boolean): Whether to use the quantized version of the model.
    • timestepType (string): The timestep type of the model. e.g., 'float32', 'int64'
  • Name
    inputs.0
    Type
    object
    Description

    An object containing the following properties:

    • prompt (string): The text prompt to generate the image.
    • strength (number): The strength of the prompt influence on the generated image. Should be between 0 and 1.
    • n_steps (number): The number of steps to run the diffusion process.
    • n_samples (number): The number of samples to generate.
    • image (string): The URL of the image to inpaint.
    • mask_image (string): The URL of the mask image indicating the areas to inpaint.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"stable-diffusion\", \"model_options\": {\"revision\": \"onnx\", \"quantized\": false }, \"inputs\": [{\"prompt\": \"Face of a yellow cat, high resolution, sitting on a park bench.\", \"strength\": 1.0, \"n_steps\": 5, \"n_samples\": 1, \"image\": \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png\", \"mask_image\": \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png\"}]}"

Response

[
  {
    "url": "blob:https://compute.peer-ai.com/55a46563-4372-4a97-9832-ac6bdff1b09f"
  }
]

Stable Diffusion 1.5 Inpainting

Stable Diffusion 1.5 Inpainting is a technique used for image inpainting, which involves filling in missing or corrupted parts of an image. It uses a generative model to generate plausible content for the missing regions based on the surrounding context. This pipeline uses the specific Stable Diffusion 1.5 inpainting model.

Body

  • Name
    task
    Type
    string
    Description

    The task of the pipeline. e.g., 'sentiment-analysis', 'text-classification'

  • Name
    model(optional)
    Type
    string, default null
    Description

    The name of the pre-trained model to use. If not specified, the default model for the task will be used.

  • Name
    model_options(optional)
    Type
    object, default null
    Description

    An object containing the following properties:

    • revision (string): The revision of the model to use. e.g., 'main', 'onnx', 'quantized'
    • quantized (boolean): Whether to use the quantized version of the model.
    • timestepType (string): The timestep type of the model. e.g., 'float32', 'int64'
  • Name
    inputs.0
    Type
    object
    Description

    An object containing the following properties:

    • prompt (string): The text prompt to generate the image.
    • n_steps (number): The number of steps to run the diffusion process.
    • n_samples (number): The number of samples to generate.
    • image (string): The URL of the image to inpaint.
    • mask_image (string): The URL of the mask image indicating the areas to inpaint.

Request

curl -X POST https://api.peer-ai.com/v1/pipeline \
  -H "X-API-Group: {YOUR_COMPUTE_GROUP}" \
  -H "X-API-Key: {YOUR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "{\"task\": \"stable-diffusion-inpaint\", \"model\": \"runwayml/stable-diffusion-inpainting\", \"model_options\": {\"revision\": \"onnx\", \"quantized\": false }, \"inputs\": [{\"prompt\": \"Face of a yellow cat, high resolution, sitting on a park bench.\", \"n_steps\": 10, \"n_samples\": 1, \"image\": \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png\", \"mask_image\": \"https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png\"}]}"

Response

[
  {
    "url": "blob:https://compute.peer-ai.com/55a46563-4372-4a97-9832-ac6bdff1b09f"
  }
]